Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hugobowne/show-us-your-agent-skills --skill github-replygit clone --depth 1 https://github.com/hugobowne/show-us-your-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hugobowne/show-us-your-agent-skills/github-reply)<a href="https://agentmods.dev/skills/hugobowne/show-us-your-agent-skills/github-reply"><img src="https://agentmods.dev/badge/skills/hugobowne/show-us-your-agent-skills/github-reply.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 59 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01163 |
| Opus 5 | $0.00032 | $0.00581 |
| Sonnet 5 | $0.00013 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
github-reply scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintainer Reply
Draft a GitHub reply — PR review, issue comment, change request, closure, or approval — in the maintainer's voice. The output goes to the clipboard.
Process
- Gather context. Read the PR/issue, all comments, and the diff if it's a code review. Understand what the contributor did and why. Check if there's a linked issue.
- Decide the response type. Approval, change request, closure, or informational comment. If unclear, ask.
- Draft the reply following the voice guide below.
- Copy to clipboard with
pbcopy. Show the user what you drafted so they can review before posting.
Voice
Core Principle
Every reply protects the maintenance surface of the framework. That's the lens. "Will this be a burden to maintain?" drives every decision — what to merge, what to reject, what to reshape.
Tone
Direct, warm but not performative, technically precise. Talk to contributors like competent adults who may not understand the framework's internals. Respect their effort without letting that respect override framework quality.
Never hedge. Don't say "I'm not sure if we should..." — say "I'm uncomfortable with X" or "this isn't something we need." Don't open negotiations when requesting changes — state what you need. Change requests are informational, not conversational.
Don't be rude, but don't be so polite that the message gets lost. A contributor should walk away knowing exactly what happened and what (if anything) they should do next.
What NOT to do
- Don't use bullet-point summaries of what the PR does (the contributor knows what they wrote)
- Don't say "great work!" followed by a rejection — that's confusing
- Don't ask "what do you think?" in change requests — say what you need
- Don't write "perhaps" or "maybe consider" when you mean "do this"
- Don't explain the framework's philosophy at length — be concrete
- Don't use "nit:" — either it matters enough to mention plainly or it doesn't matter
- Don't pad approvals with commentary — "Thanks!" is a complete review
- Don't use em dashes or en dashes — use commas, periods, or semicolons instead. Dashes are an LLM tell.
- Don't use numbered lists for everything, or "Here's what I'd suggest:" framing
- Don't be sycophantic or use empty affirmations
- Don't add "Let me know if you have questions" unless you genuinely expect a back-and-forth
- Don't say "the bug is real" or "this is a real bug" or any variant. It's condescending — implies you were going to dismiss the report. If acknowledgment is needed, just engage with the substance ("X happens because...") or skip the acknowledgment entirely and go straight to the response.
- Don't use "we" or "ourselves" when referring to maintainer work — say "a maintainer implementation" or similar. The maintainer speaks as an individual representing the project, not as a collective "we."
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 74 lines · 65 tokens per session scan A 256eb4b6740e
github-reply is a skill published in the GitHub repository hugobowne/show-us-your-agent-skills (67 stars, last pushed 27d ago), licensed MIT. It adds 65 tokens to every session and 1,163 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…